BatGPT-Chem: A Foundation Large Model For Retrosynthesis Prediction
This work addresses the problem of limited generalization and alternative pathway exploration in AI-based retrosynthesis tools for chemists and drug discovery researchers, representing a strong specific gain rather than an incremental improvement.
The paper tackles the challenge of retrosynthesis prediction in drug discovery by introducing BatGPT-Chem, a 15-billion-parameter large language model that integrates chemical tasks via natural language and SMILES notation, achieving superior performance over existing AI methods in generating effective strategies for complex molecules as validated by benchmark tests.
Retrosynthesis analysis is pivotal yet challenging in drug discovery and organic chemistry. Despite the proliferation of computational tools over the past decade, AI-based systems often fall short in generalizing across diverse reaction types and exploring alternative synthetic pathways. This paper presents BatGPT-Chem, a large language model with 15 billion parameters, tailored for enhanced retrosynthesis prediction. Integrating chemical tasks via a unified framework of natural language and SMILES notation, this approach synthesizes extensive instructional data from an expansive chemical database. Employing both autoregressive and bidirectional training techniques across over one hundred million instances, BatGPT-Chem captures a broad spectrum of chemical knowledge, enabling precise prediction of reaction conditions and exhibiting strong zero-shot capabilities. Superior to existing AI methods, our model demonstrates significant advancements in generating effective strategies for complex molecules, as validated by stringent benchmark tests. BatGPT-Chem not only boosts the efficiency and creativity of retrosynthetic analysis but also establishes a new standard for computational tools in synthetic design. This development empowers chemists to adeptly address the synthesis of novel compounds, potentially expediting the innovation cycle in drug manufacturing and materials science. We release our trial platform at \url{https://www.batgpt.net/dapp/chem}.